全站搜索

AI 模型 84760

• Strangemerges_32Yamshadow-7B-GGUF↗

  MaziyarPanahi

• Qwen3.6-35B-A3B-Uncensored-MTP-GGUF↗

  mecha-factory

  **This is an uncensored model.** Its refusals were trained out by its author, so it answers what the base model would decline. You are responsible for how you use it. HauhauCS's uncensored Qwen3.6-35B-A3B at Q4_K_M, with the multi-token-prediction (MTP) head from unsloth's conversion of the original model grafted on, so llama.cpp can draft with it (`--spec-type draft-mtp`). This is the file mecha installs as the catalog model `qwen3.6-35b-a3b-uncensored`; hosting it saves building the graft locally. Nothing was retrained or requantized. The file was made by `scripts/mtp-graft.py` (gguf 0.19.0, numpy 2.5.3) from two inputs:

• Llama-3.2-3B-Instruct-q4f16_0-MLC↗

  mlc-ai

• MiniCPM-V-4.7-1B-OptiQ-4bit↗

  mlx-community

• Nanbeige4.2-3B-OptiQ-4bit↗

  mlx-community

• swahili-Instruct-llama-2-7b↗

  Mollel

• Angry-Claudius-9B-GGUF↗

  mradermacher

• Calyx_7B-i1-GGUF↗

  mradermacher

• CursorCore-QW2.5-7B-GGUF↗

  mradermacher

• CyberWitch-7B-i1-GGUF↗

  mradermacher